© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 62081
    Prev
    Next
    INDEX
    Explanations

    references to tabs within a user interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orio
    -0.08
    UMB
    -0.08
    edException
    -0.07
    inç
    -0.07
    mtree
    -0.07
    BUFFER
    -0.07
    vale
    -0.07
    UNET
    -0.07
    enticate
    -0.07
    eous
    -0.07
    POSITIVE LOGITS
    ular
    0.10
    lix
    0.10
    bed
    0.10
    bing
    0.09
    bedPane
    0.09
    ulator
    0.08
    bers
    0.08
    sets
    0.07
    loid
    0.07
    ber
    0.07
    Activations Density 0.014%

    No Known Activations